Re: [RFC][PATCH][bugfix] more checks for negative f_pos handling v4

[Wu Fengguang <fengguang.wu@intel.com>]

On Thu, Sep 17, 2009 at 03:23:24PM +0800, KAMEZAWA Hiroyuki wrote:
> On Thu, 17 Sep 2009 15:14:28 +0800
> Wu Fengguang <fengguang.wu@intel.com> wrote:
> 
> > On Thu, Sep 17, 2009 at 02:51:00PM +0800, KAMEZAWA Hiroyuki wrote:
> > > From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
> > > 
> > > Now, rw_verify_area() checsk f_pos is negative or not. And if
> > > negative, returns -EINVAL.
> > > 
> > > But, some special files as /dev/(k)mem and /proc/<pid>/mem etc..
> > > has negative offsets. And we can't do any access via read/write
> > > to the file(device).
> > > 
> > > This patch introduce a flag S_VERYBIG and allow negative file
> > > offsets for big files. (usual files don't allow it.)
> > > 
> > > Changelog: v3->v4
> > >  - make changes in mem.c aligned.
> > >  - change __negative_fpos_check() to return int. 
> > >  - fixed bug in "pos" check.
> > >  - added comments.
> > > 
> > > Changelog: v2->v3
> > >  - fixed bug in rw_verify_area (it cannot be compiled)
> > > 
> > > Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
> > > ---
> > >  drivers/char/mem.c |   23 +++++++++++++----------
> > >  fs/proc/base.c     |    2 ++
> > >  fs/read_write.c    |   22 ++++++++++++++++++++--
> > >  include/linux/fs.h |    2 ++
> > >  4 files changed, 37 insertions(+), 12 deletions(-)
> > > 
> > > Index: mmotm-2.6.31-Sep14/fs/read_write.c
> > > ===================================================================
> > > --- mmotm-2.6.31-Sep14.orig/fs/read_write.c
> > > +++ mmotm-2.6.31-Sep14/fs/read_write.c
> > > @@ -205,6 +205,21 @@ bad:
> > >  }
> > >  #endif
> > >  
> > > +static int
> > > +__negative_fpos_check(struct inode *inode, loff_t pos, size_t count)
> > > +{
> > > +	/*
> > > +	 * pos or pos+count is negative here, check overflow.
> > > +	 * too big "count" will be caught in rw_verify_area().
> > > +	 */
> > > +	if ((pos < 0) && (pos + count < pos))
> > > +		return -EOVERFLOW;
> > 
> > This returns -EOVERFLOW when pos=-10 and count=1. What's the intention?
>   Hmm ?
> 
>   pos+count=-9 > -10 ? it's ok. no -EOVERFLOW
> 
>   pos=-10, count=11, 
>   pos+count=1 > -10, then overflow.

Ah yes, was confused..

> > Just to return a different error code other than -EINVAL?
> > 
> For showing what this "if" checks. EINVAL is better ?

..so please ignore this question.

Thanks,
Fengguang

> 
> > Also it seems you did two behavior changes at the same time: the above
> > -EOVERFLOW and the below IS_VERYBIG(). Are they tightly coupled?
> > 
> > > +	/* If !VERYBIG inode, negative pos(pos+count) is not allowed */
> > > +	if (!IS_VERYBIG(inode))
> > > +		return -EINVAL;
> > > +	return 0;
> > > +}
> > > +
> > >  /*
> > >   * rw_verify_area doesn't like huge counts. We limit
> > >   * them to something that fits in "int" so that others
> > > @@ -222,8 +237,11 @@ int rw_verify_area(int read_write, struc
> > >  	if (unlikely((ssize_t) count < 0))
> > >  		return retval;
> > >  	pos = *ppos;
> > > -	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
> > > -		return retval;
> > > +	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) {
> > > +		retval = __negative_fpos_check(inode, pos, count);
> > > +		if (retval)
> > > +			return retval;
> > > +	}
> > 
> > This could look more nicer:
> > 
> >         retval = __negative_fpos_check(inode, pos, count);
> >         if (retval)
> >                 return retval;
> > 
> > But they are all minor issues :)
> > 
> > Thanks,
> > Fengguang
> > 
> > >  
> > >  	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
> > >  		retval = locks_mandatory_area(
> > > Index: mmotm-2.6.31-Sep14/include/linux/fs.h
> > > ===================================================================
> > > --- mmotm-2.6.31-Sep14.orig/include/linux/fs.h
> > > +++ mmotm-2.6.31-Sep14/include/linux/fs.h
> > > @@ -231,6 +231,7 @@ struct inodes_stat_t {
> > >  #define S_NOCMTIME	128	/* Do not update file c/mtime */
> > >  #define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
> > >  #define S_PRIVATE	512	/* Inode is fs-internal */
> > > +#define S_VERYBIG	1024	/* Allow file's loff_t can be negative */
> > >  
> > >  /*
> > >   * Note that nosuid etc flags are inode-specific: setting some file-system
> > > @@ -265,6 +266,7 @@ struct inodes_stat_t {
> > >  #define IS_NOCMTIME(inode)	((inode)->i_flags & S_NOCMTIME)
> > >  #define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
> > >  #define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
> > > +#define IS_VERYBIG(inode)	((inode)->i_flags & S_VERYBIG)
> > >  
> > >  /* the read-only stuff doesn't really belong here, but any other place is
> > >     probably as bad and I don't want to create yet another include file. */
> > > Index: mmotm-2.6.31-Sep14/drivers/char/mem.c
> > > ===================================================================
> > > --- mmotm-2.6.31-Sep14.orig/drivers/char/mem.c
> > > +++ mmotm-2.6.31-Sep14/drivers/char/mem.c
> > > @@ -825,22 +825,23 @@ static const struct memdev {
> > >  	const char *name;
> > >  	const struct file_operations *fops;
> > >  	struct backing_dev_info *dev_info;
> > > +	bool	verybig;
> > >  } devlist[] = {
> > > -	[ 1] = { "mem", &mem_fops, &directly_mappable_cdev_bdi },
> > > +	[1]  = { "mem", &mem_fops, &directly_mappable_cdev_bdi, true },
> > >  #ifdef CONFIG_DEVKMEM
> > > -	[ 2] = { "kmem", &kmem_fops, &directly_mappable_cdev_bdi },
> > > +	[2]  = { "kmem", &kmem_fops, &directly_mappable_cdev_bdi, true },
> > >  #endif
> > > -	[ 3] = {"null", &null_fops, NULL },
> > > +	[3]  = {"null", &null_fops, NULL, false },
> > >  #ifdef CONFIG_DEVPORT
> > > -	[ 4] = { "port", &port_fops, NULL },
> > > +	[4]  = { "port", &port_fops, NULL, false },
> > >  #endif
> > > -	[ 5] = { "zero", &zero_fops, &zero_bdi },
> > > -	[ 6] = { "full", &full_fops, NULL },
> > > -	[ 7] = { "random", &random_fops, NULL },
> > > -	[ 9] = { "urandom", &urandom_fops, NULL },
> > > -	[11] = { "kmsg", &kmsg_fops, NULL },
> > > +	[5]  = { "zero", &zero_fops, &zero_bdi, false },
> > > +	[6]  = { "full", &full_fops, NULL, false },
> > > +	[7]  = { "random", &random_fops, NULL, false },
> > > +	[9]  = { "urandom", &urandom_fops, NULL, false },
> > > +	[11] = { "kmsg", &kmsg_fops, NULL, false },
> > >  #ifdef CONFIG_CRASH_DUMP
> > > -	[12] = { "oldmem", &oldmem_fops, NULL },
> > > +	[12] = { "oldmem", &oldmem_fops, NULL, false },
> > >  #endif
> > >  };
> > >  
> > > @@ -868,6 +869,8 @@ static int memory_open(struct inode *ino
> > >  		ret = dev->fops->open(inode, filp);
> > >  	else
> > >  		ret = 0;
> > > +	if (dev->verybig)
> > > +		inode->i_flags |= S_VERYBIG;
> > >  out:
> > >  	unlock_kernel();
> > >  	return ret;
> > > Index: mmotm-2.6.31-Sep14/fs/proc/base.c
> > > ===================================================================
> > > --- mmotm-2.6.31-Sep14.orig/fs/proc/base.c
> > > +++ mmotm-2.6.31-Sep14/fs/proc/base.c
> > > @@ -779,6 +779,8 @@ static const struct file_operations proc
> > >  static int mem_open(struct inode* inode, struct file* file)
> > >  {
> > >  	file->private_data = (void*)((long)current->self_exec_id);
> > > +	/* this file is read only and we can catch out-pf-range */
> > > +	inode->i_flags |= S_VERYBIG;
> > >  	return 0;
> > >  }
> > >  
> >